diff options
| -rw-r--r-- | youtube_dl/extractor/eroprofile.py | 40 |
1 files changed, 16 insertions, 24 deletions
diff --git a/youtube_dl/extractor/eroprofile.py b/youtube_dl/extractor/eroprofile.py index f6745fc52..79e2fbd39 100644 --- a/youtube_dl/extractor/eroprofile.py +++ b/youtube_dl/extractor/eroprofile.py @@ -1,53 +1,45 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor + class EroProfileIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<display_id>[^/]+)' + _VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<id>[^/]+)' _TEST = { 'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore', 'md5': 'c26f351332edf23e1ea28ce9ec9de32f', 'info_dict': { 'id': '3733775', + 'display_id': 'sexy-babe-softcore', 'ext': 'm4v', - 'title': 'HD MOVIES - sexy babe softcore', - 'description': 'md5:831ee50526c333eb4f6c1e58d382c295', - 'categories': list, # NSFW + 'title': 'sexy babe softcore', 'thumbnail': 're:https?://.*\.jpg', 'age_limit': 18, } } def _real_extract(self, url): - webpage = self._download_webpage(url, 'main') + display_id = self._match_id(url) - video_id = self._html_search_regex(r'glbUpdViews\s*\(\'\d*\',\'(\d+)\'', webpage, 'id') + webpage = self._download_webpage(url, display_id) - video_url = self._html_search_regex(r'<source src="([^"]+)', webpage, 'video_url') + video_id = self._search_regex( + [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'], + webpage, 'video id', default=None) + video_url = self._search_regex( + r'<source src="([^"]+)', webpage, 'video url') title = self._html_search_regex( - r'<title>([^<]+)\s*-\s*EroProfile</title>', webpage, 'title') - - description = self._html_search_meta('description', webpage, 'description', fatal=False) - - thumbnail = self._html_search_regex( - r'onclick="showVideoPlayer\(\)"><img src="([^"]+)', webpage, 'thumbnail', fatal=False) - - categories_str = self._html_search_meta( - 'keywords', webpage, 'categories', fatal=False) - categories = ( - None if categories_str is None - else categories_str.split(',')) + r'Title:</th><td>([^<]+)</td>', webpage, 'title') + thumbnail = self._search_regex( + r'onclick="showVideoPlayer\(\)"><img src="([^"]+)', + webpage, 'thumbnail', fatal=False) return { 'id': video_id, + 'display_id': display_id, 'url': video_url, 'title': title, - 'ext': 'm4v', - 'description': description, 'thumbnail': thumbnail, - 'categories': categories, 'age_limit': 18, } |